A Hybrid Deep Learning Model for Face Sketch Recognition

Hussein Samma; Shahrel Azmin Suandi; Junita Mohamad-Saleh

doi:10.1007/978-981-16-8129-5_83

A Hybrid Deep Learning Model for Face Sketch Recognition

Hussein Samma^*
, Shahrel Azmin Suandi
, Junita Mohamad-Saleh

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Scopus citations

Abstract

This paper introduces a hybrid deep learning model which integrates particle swarm optimization (PSO) with VGG-face deep learning network for face sketch recognition problem. Particularly, the proposed hybrid model incorporates PSO into VGG-face to find the best filters of the last layer that have the highest contribution in face sketch recognition. In addition, PSO performs fine-tuning for the selected filter to enhance recognition rate accuracy. To assess the performances of the proposed hybrid model, LFW face sketch benchmark images are used in this study. Reported results show that PSO can reduce VGG- face model complexity and increase recognition accuracy to 76% on LFW benchmark images.

Original language	English
Title of host publication	Proceedings of the 11th International Conference on Robotics, Vision, Signal Processing and Power Applications - Enhancing Research and Innovation through the Fourth Industrial Revolution
Editors	Nor Muzlifah Mahyuddin, Nor Rizuan Mat Noor, Harsa Amylia Mat Sakim
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	545-551
Number of pages	7
ISBN (Print)	9789811681288
DOIs	https://doi.org/10.1007/978-981-16-8129-5_83
State	Published - 2022
Externally published	Yes
Event	11th International Conference on Robotics, Vision, Signal Processing and Power Applications, RoViSP 2021 - Virtual, Online Duration: 5 Apr 2021 → 6 Apr 2021

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	829 LNEE
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	11th International Conference on Robotics, Vision, Signal Processing and Power Applications, RoViSP 2021
City	Virtual, Online
Period	5/04/21 → 6/04/21

Bibliographical note

Publisher Copyright:
© 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Keywords

Deep learning
Face sketch recognition
Particle swarm optimization
VGG-face

ASJC Scopus subject areas

Industrial and Manufacturing Engineering

Access to Document

10.1007/978-981-16-8129-5_83

Cite this

Samma, H., Suandi, S. A., & Mohamad-Saleh, J. (2022). A Hybrid Deep Learning Model for Face Sketch Recognition. In N. M. Mahyuddin, N. R. Mat Noor, & H. A. Mat Sakim (Eds.), Proceedings of the 11th International Conference on Robotics, Vision, Signal Processing and Power Applications - Enhancing Research and Innovation through the Fourth Industrial Revolution (pp. 545-551). (Lecture Notes in Electrical Engineering; Vol. 829 LNEE). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-16-8129-5_83

Samma, Hussein ; Suandi, Shahrel Azmin ; Mohamad-Saleh, Junita. / A Hybrid Deep Learning Model for Face Sketch Recognition. Proceedings of the 11th International Conference on Robotics, Vision, Signal Processing and Power Applications - Enhancing Research and Innovation through the Fourth Industrial Revolution. editor / Nor Muzlifah Mahyuddin ; Nor Rizuan Mat Noor ; Harsa Amylia Mat Sakim. Springer Science and Business Media Deutschland GmbH, 2022. pp. 545-551 (Lecture Notes in Electrical Engineering).

@inproceedings{afdf587743db44ad86aa14f5e96ad457,

title = "A Hybrid Deep Learning Model for Face Sketch Recognition",

abstract = "This paper introduces a hybrid deep learning model which integrates particle swarm optimization (PSO) with VGG-face deep learning network for face sketch recognition problem. Particularly, the proposed hybrid model incorporates PSO into VGG-face to find the best filters of the last layer that have the highest contribution in face sketch recognition. In addition, PSO performs fine-tuning for the selected filter to enhance recognition rate accuracy. To assess the performances of the proposed hybrid model, LFW face sketch benchmark images are used in this study. Reported results show that PSO can reduce VGG- face model complexity and increase recognition accuracy to 76\% on LFW benchmark images.",

keywords = "Deep learning, Face sketch recognition, Particle swarm optimization, VGG-face",

author = "Hussein Samma and Suandi, \{Shahrel Azmin\} and Junita Mohamad-Saleh",

note = "Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; 11th International Conference on Robotics, Vision, Signal Processing and Power Applications, RoViSP 2021 ; Conference date: 05-04-2021 Through 06-04-2021",

year = "2022",

doi = "10.1007/978-981-16-8129-5\_83",

language = "English",

isbn = "9789811681288",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "545--551",

editor = "Mahyuddin, \{Nor Muzlifah\} and \{Mat Noor\}, \{Nor Rizuan\} and \{Mat Sakim\}, \{Harsa Amylia\}",

booktitle = "Proceedings of the 11th International Conference on Robotics, Vision, Signal Processing and Power Applications - Enhancing Research and Innovation through the Fourth Industrial Revolution",

address = "Germany",

}

Samma, H, Suandi, SA & Mohamad-Saleh, J 2022, A Hybrid Deep Learning Model for Face Sketch Recognition. in NM Mahyuddin, NR Mat Noor & HA Mat Sakim (eds), Proceedings of the 11th International Conference on Robotics, Vision, Signal Processing and Power Applications - Enhancing Research and Innovation through the Fourth Industrial Revolution. Lecture Notes in Electrical Engineering, vol. 829 LNEE, Springer Science and Business Media Deutschland GmbH, pp. 545-551, 11th International Conference on Robotics, Vision, Signal Processing and Power Applications, RoViSP 2021, Virtual, Online, 5/04/21. https://doi.org/10.1007/978-981-16-8129-5_83

A Hybrid Deep Learning Model for Face Sketch Recognition. / Samma, Hussein; Suandi, Shahrel Azmin; Mohamad-Saleh, Junita.
Proceedings of the 11th International Conference on Robotics, Vision, Signal Processing and Power Applications - Enhancing Research and Innovation through the Fourth Industrial Revolution. ed. / Nor Muzlifah Mahyuddin; Nor Rizuan Mat Noor; Harsa Amylia Mat Sakim. Springer Science and Business Media Deutschland GmbH, 2022. p. 545-551 (Lecture Notes in Electrical Engineering; Vol. 829 LNEE).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Hybrid Deep Learning Model for Face Sketch Recognition

AU - Samma, Hussein

AU - Suandi, Shahrel Azmin

AU - Mohamad-Saleh, Junita

PY - 2022

Y1 - 2022

N2 - This paper introduces a hybrid deep learning model which integrates particle swarm optimization (PSO) with VGG-face deep learning network for face sketch recognition problem. Particularly, the proposed hybrid model incorporates PSO into VGG-face to find the best filters of the last layer that have the highest contribution in face sketch recognition. In addition, PSO performs fine-tuning for the selected filter to enhance recognition rate accuracy. To assess the performances of the proposed hybrid model, LFW face sketch benchmark images are used in this study. Reported results show that PSO can reduce VGG- face model complexity and increase recognition accuracy to 76% on LFW benchmark images.

AB - This paper introduces a hybrid deep learning model which integrates particle swarm optimization (PSO) with VGG-face deep learning network for face sketch recognition problem. Particularly, the proposed hybrid model incorporates PSO into VGG-face to find the best filters of the last layer that have the highest contribution in face sketch recognition. In addition, PSO performs fine-tuning for the selected filter to enhance recognition rate accuracy. To assess the performances of the proposed hybrid model, LFW face sketch benchmark images are used in this study. Reported results show that PSO can reduce VGG- face model complexity and increase recognition accuracy to 76% on LFW benchmark images.

KW - Deep learning

KW - Face sketch recognition

KW - Particle swarm optimization

KW - VGG-face

UR - https://www.scopus.com/pages/publications/85125236762

U2 - 10.1007/978-981-16-8129-5_83

DO - 10.1007/978-981-16-8129-5_83

M3 - Conference contribution

AN - SCOPUS:85125236762

SN - 9789811681288

T3 - Lecture Notes in Electrical Engineering

SP - 545

EP - 551

BT - Proceedings of the 11th International Conference on Robotics, Vision, Signal Processing and Power Applications - Enhancing Research and Innovation through the Fourth Industrial Revolution

A2 - Mahyuddin, Nor Muzlifah

A2 - Mat Noor, Nor Rizuan

A2 - Mat Sakim, Harsa Amylia

PB - Springer Science and Business Media Deutschland GmbH

T2 - 11th International Conference on Robotics, Vision, Signal Processing and Power Applications, RoViSP 2021

Y2 - 5 April 2021 through 6 April 2021

ER -

Samma H, Suandi SA, Mohamad-Saleh J. A Hybrid Deep Learning Model for Face Sketch Recognition. In Mahyuddin NM, Mat Noor NR, Mat Sakim HA, editors, Proceedings of the 11th International Conference on Robotics, Vision, Signal Processing and Power Applications - Enhancing Research and Innovation through the Fourth Industrial Revolution. Springer Science and Business Media Deutschland GmbH. 2022. p. 545-551. (Lecture Notes in Electrical Engineering). doi: 10.1007/978-981-16-8129-5_83

A Hybrid Deep Learning Model for Face Sketch Recognition

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this